© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4059
    Prev
    Next
    INDEX
    Explanations

    storage or permanence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kecamatan
    0.37
     و
    0.33
    🚀
    0.33
     Teknik
    0.32
    unarod
    0.32
     megy
    0.32
     turun
    0.32
    ސ
    0.32
    मेट
    0.31
    리스
    0.31
    POSITIVE LOGITS
     storing
    0.47
     과거
    0.41
    storage
    0.39
     permanent
    0.39
    Stored
    0.39
     stored
    0.38
     storage
    0.38
     armazenamento
    0.38
     ইতিহাস
    0.38
    permanent
    0.37
    Activations Density 0.809%

    No Known Activations